FIELD OF INVENTION

THIS invention relates to medical testing systems and methods, to remote cloud-based testing systems and methods, particularly to remote diagnosis systems and methods for providing test results possibly including a related diagnosis to a person at a testing location typically in the form of a point of Care (POC) location.

BACKGROUND OF INVENTION

Point of Care (POC) testing systems for certain diseases and viruses generally have and make use of medical diagnostic equipment which tests samples extracted from human or animal bodies for one or more diseases and/or infections. Testing equipment usually generates data which are interpreted by suitable clinicians that make diagnoses at POC locations or facilities such as hospitals, clinics, testing/quarantine zones, etc.

In some cases, POC testing systems make use of medical diagnostic equipment in the form of real-time polymerase chain reaction (PCR/qPCR, herein referred to as “PCR” for brevity) test equipment to identify certain diseases such as COVID-19.

Commercially available PCR test equipment receive samples of genetic material for testing and process the same in a conventional manner at a POC location. The equipment typically outputs results of the processing to a suitable graphical user interface which is interpreted by suitably trained clinicians. These clinicians make diagnoses based on the results displayed by the PCR test equipment. A difficulty in times of pandemic, for example, during the COVID-19 pandemic, is that there are large numbers of people requiring testing to identify whether or not they have contracted COVID-19. However, there are often not enough suitably trained clinicians to be able to interpret the PCR test equipment and provide a diagnosis at a POC location in real-time/near-real time.

This problem is exacerbated when one considers the lack of visibility of test results generated in a POC setting and a backlog of patients waiting at POC locations such as healthcare facilities (e.g., hospitals and clinics, etc.) for test results, said patients occupying valuable beds and wasting valuable resources.

There exists a great need for point of care diagnostic equipment that does not require a trained clinician at the point of care.

Healthcare systems have many existing devices, which could be repurposed for testing for COVID-19 but they still have to rely on scarce skilled experts to interpret the test data. This causes extended and expensive (and potentially infectious) delays between time of testing and time of diagnosis.

The Inventors are aware of disclosures which seek to provide automatic classification of PCR Amplification curves in order to interpret PCR test data, for example, “Rodiger (2019) EConferences: "Fundamentals for the Automatic Classification of Quantitative PCR Amplificationcurves - A Biostatistical Approach - eConferences” and quantitative PCR analysis toolkits and associated documentation such as an anonymous “PCRedux package - an overview”.

WO 2017/025589 A1 discloses an approach which uses melting curves of qPCR reactions for the purpose of classification by extracting features (classifiers) from the melt curves to calculate a characteristic signature thereof and feeding the signature to a trained machine learning algorithm to determine the presence or absence as well as quality of a target nucleic acid. Moniri ET AL (2019) Analytical Chemistry 91 , 7426-7434 discloses a multiparameter approach for the quantification of target nucleic acid probes in a sample by combining existing standard curve methods into a multidimensional standard curve. In particular, by considering multiple features together such that each amplification curve is viewed as a point in a multidimensional space.

Despite attempting to provide automatic classification of PCR data and, in the case of the last-mentioned disclosure, optimise performance and increase reliability of quantification, a drawback of these disclosures is that they are unable to adapt to detect new strains and/or mutations of certain viruses which decreases detection accuracy performance of the associated methodologies.

It follows that it is an object of the present invention to address and ameliorate the problems and difficulties described herein.

SUMMARY OF INVENTION

According to one aspect of the invention, there is provided a method of providing test results associated with biological sample tested at a testing location, wherein the method comprises: receiving, by a processor at a classification location, test data acquired from medical test equipment located at a test location, wherein the test data is associated with a test conducted on a biological test sample from a person by the medical test equipment; processing the received test data with a classifier trained with, or configured to use, classification data stored in a classification database to determine a corresponding test result in an automated fashion, wherein the test result is provided with a performance measurement associated with the determination; and transmitting results data indicative of the corresponding test result to a suitable computing device associated with the test location; wherein if the performance measurement associated with the classification is below a predetermined threshold, the method comprises: transmitting the test data, or data associated therewith, to a computing device associated with a clinician capable of interpreting the test data; receiving a test result corresponding to the transmitted test data, or data associated therewith, from the computing device associated with the clinician; and updating the classification database with the test data, or data associated therewith, and the corresponding test result received from the computing device associated with the clinician; and wherein if the performance measurement associated with the classification is above the predetermined threshold, the method comprises: randomly selecting and transmitting the test data, or data associated therewith, to a computing device associated with a clinician capable of interpreting the test data; receiving a test result corresponding to the transmitted test data, or data associated therewith, from the computing device associated with the clinician; and if necessary, updating the classification database with the test data, or data associated therewith, and the corresponding test result received from the computing device associated with the clinician.

It will be appreciated that in this way, variants or mutations of certain viruses or target pathogens sought to be detected are able to be included in the classification database for subsequent detection in an automated manner by automatically transmitting the test data to a clinician and updating the test data accordingly, if necessary, based on the performance measurement. The performance measurement may be a value or percentage value which determines the accuracy of the classification by the classifier. In this regard, it may be a value which relates the determined test result, and associated data, to the classification data. In particular, the performance measurement is the degree to which the test result, and associated the data, matches the classification data stored in the database.

Similarly, in the case of the machine learning based (ML) classifier trained by the classification data stored in the classification database, the performance measurement may be the accuracy or confidence value, for example, a percentage value associated with the classification of the test results. The terms “classifying”, “classify”, and “classification” may be used interchangeably herein with the terms “determining”, “determine”, and "determination" unless otherwise stated or evident to those skilled in the field of invention.

The performance measurement may be referred to interchangeably herein as a “performance measure”, “performance measurement value”, or “performance measure value” as the case may be.

The performance threshold may be between 95% and 99%. In particular, the performance threshold may be 95%.

In some example embodiments, the results data may comprise a suitable prescription for appropriate medication for the specific patient and/or test result. The prescription (where applicable) should then be printed at the test location and medication provided to the patient.

The clinician may be a validation clinician which may be a suitably qualified person capable of interpreting the test data in one or more forms of data level abstraction, for example, graphics PCR curves, or raw data on which the curves are based. The validation clinician may thus be a virologist, immunologist, a general practitioner, or other suitably qualified medically trained person capable of interpreting the test data.

The classification location may be a cloud-based location separate from the test location. The classification location may be at the testing location as part of a local cloud-based system, or another geographically separate location. Instead, the classification location may be any location removed from and/or outside of the test equipment. The classification location may be server based. The step of processing the received test data with classification data may comprise: extracting a data signature from the received test data; comparing the extracted data signature to classification data stored in the classification database, wherein the classification data comprises a plurality of data signatures and test results corresponding thereto; and determining a test result based on said comparing.

The test result may be determined based on a match between the extracted data signature and a data signature stored in the classification database which is associated with the respective test result. The comparison may be to match the extracted data signature with an identical or substantially similar data signature stored in the classification database. It follows that in some example embodiments, the data signatures may have a degree of variance when comparing the same in the manner contemplated herein.

The method may comprise updating the classification data stored in the classification database with the test data, the data signature, or both and the corresponding test result received from the computing device associated with the clinician if the test data, the data signature, or both are not previously stored as classification data in the classification database. In this way, the classification database is being continually updated with input from an authorised clinician. In this regard, the clinician may be a suitable nurse, doctor, medical technician, etc. able and/or authorised to classify and/or read and/or interpret test data to provide test results.

The method may comprise transmitting results data indicative of the test result received from the computing device associated with the clinician to the suitable computing device associated with the test location. It will be noted that test results may be determined in an automated fashion by the processor but if the processor cannot perform the automatic determination of the test result or in other words the classification, the method conveniently comprises directing the test data to the authorised clinician to provide the test result which is then transmitted back to the test or point of care (POC) location and substantially simultaneously, the classification database is conveniently updated with the previously unclassified test data, particularly the corresponding data signature and corresponding test result, so that similar future test data may be classified in an automated fashion. It follows that the method may comprise tracking the test data transmitted to the clinician and associating the extracted data signature with the test result received from the clinician related to the transmitted test data.

The one or more predetermined conditions for transmitting the test data, or data associated therewith, to the computing device associated with at least one predetermined clinician may be one or both of where the step of processing the received test data with classification data does not result in the determination of a test result, and for testing of accuracy of the processing step. In this way, the test data is only transmitted to the clinician if the processor cannot make an automatic comparison in a manner described herein or for random testing of the classification accuracy of the classification described herein. It will be noted that in some example embodiments, more conditions may be present for having the clinician provide a test result.

Nothing precludes the test data being transmitted to a plurality of clinicians. In some example embodiments, only upon the classification of the test data by more than one clinician may the database be updated in the manner contemplated herein and/or the test result transmitted to the test location computing device. In this example embodiment, only upon consensus between two or more clinicians will the test result be valid. In other example embodiments, only the test result received from the clinician which responds is considered a valid test result to update the database with and transmit to the test location.

The method may comprise receiving patient data associated with the person associated with the test data, wherein the method comprises storing the patient data and transmitting the patient data with the test data, or data associated therewith, to the computing device associated with the clinician. The computing devices associated with the test location, and associated with the clinician may have stored thereon computer software which facilitates communication between the processor and classification database. The method may comprise maintaining the classification database, wherein the classification database stores classification data comprising data signatures, and corresponding test results; and wherein the method comprises maintaining a patient database storing patient data associated with people associated with the biological sample being tested, wherein at least some of the patient data is stored for a shorter period of time than the classification data.

The test data may be one or more of an image of a suitable test graph/s generated by the medical test equipment and displayed by a suitable display device associated with the medical test equipment, the suitable test graph/s generated by the medical test equipment, and numerical data associated with the test graph/s generated by the medical test equipment.

The method may comprise one or both of capturing an image of the suitable of graph/s displayed by the display devices associated with the medical test equipment by way of a suitable test data capturing device provided adjacent the medical test equipment, and interfacing a suitable test data capturing device with the medical test equipment so that the suitable test data capturing device is in data communication with the medical test equipment to acquire the suitable test graph/s generated by the medical test equipment and/or the numerical data associated with the test graph/s generated by the medical test equipment.

The method comprises receiving the test data from the suitable data capturing device interfaced with the medical test equipment.

Where the test data comprises images taken of a display screen displaying test results, the method may comprise using image processing techniques on the test data to determine the test result.

The medical test equipment may typically be in the form of a polymerase chain reaction (PCR) test equipment. In this regard, the test data may be one or more of an image of a suitable PCR graph/s generated by the PCR test equipment and displayed by a suitable display device associated with the PCR test equipment, test graph/s generated by the PCR test equipment, and numerical data associated with test graph/s generated by the PCR test equipment.

The test data may be an image of a suitable PCR graph/s generated by the PCR test equipment, the method comprises scaling the image by performing curve fitting on pixel data associated with the image, then substituting cartesian pixel coordinates in fitted curve with pixel data. As mentioned above, the method may comprise applying image processing techniques/algorithms to the test data comprising images in an automated fashion. This is of course counterintuitive to test equipment which processes raw data generated thereby as no image processing techniques are used. This conveniently makes the disclosure herein equipment manufacturer invariant or agnostic.

The method may comprise determining whether or not the test data is valid by determining whether or not both positive and negative control curves, or data representative thereof, are present in the test data, and that a growth coefficient of a test result curve in Phase 1 of the test data is multiplying by a factor of between 1 .8 and 2 per cycle.

The step of extracting the data signature may only carried out after the test data is determined to be valid. It will be noted that extracting the data signature from the test data may comprise: determining start and end points of Phase 2 of a test result curve, or data representative thereof; and determining a gradient of the test result curve in Phase 2, or data representative thereof, wherein at least the determined start and end points of Phase 2 of the test result curve and the determined gradient, or data representative thereof, form all or part of the data signature.

The method may comprise interfacing the test data capturing device with the medical test equipment, wherein the test data capturing device is configured to capture images of a display associated with the medical test device, extract data from a suitable communication interface, or both. It will be appreciated from the foregoing that classification by the classifier which is below the performance threshold has the benefit of automatic transmission of the test data to a clinician and automatic reception and updating of the classification database. Moreover, classification by the classifier which is above the performance threshold has the benefit of a random selection of test data for automatic transmission to a clinician and automatic reception and updating of the classification database, if necessary, so as to be able to detect and/or classify mutations, different strains, or the like of viruses.

According to another aspect of the invention, there is provided a system for providing test results associated with biological samples tested at a testing location, wherein the system comprises: a classification database storing classification data; a suitable communication module; and a processor arrangement coupled to the classification database and the communication module, wherein the processor is configured to: receive test data acquired from medical test equipment located at a test location, wherein the test data is associated with a test conducted on a biological test sample from a person by the medical test equipment; process the received test data with a classifier trained with, or configured to use, the classification data stored in a classification database to determine a corresponding test result in an automated fashion, wherein the test result is provided with a performance measurement associated with the determination; and transmit, via the communication module, results data indicative of the corresponding test result to a suitable computing device associated with the test location; wherein if the performance measurement associated with the classification is below a predetermined threshold, the processor is further configured to: transmit the test data, or data associated therewith, to a computing device associated with a clinician capable of interpreting the test data via the communication module; receive a test result corresponding to the transmitted test data, or data associated therewith, from the computing device associated with the clinician via the communication module; and update the classification database with the test data, or data associated therewith, and the corresponding test result received from the computing device associated with the clinician; and wherein if the performance measurement associated with the classification is above the predetermined threshold, the processor is configured to: randomly select and transmit the test data, or data associated therewith, to a computing device associated with a clinician capable of interpreting the test data; receive a test result corresponding to the transmitted test data, or data associated therewith, from the computing device associated with the clinician; and if necessary, update the classification database with the test data, or data associated therewith, and the corresponding test result received from the computing device associated with the clinician.

The processor may be configured to process the received test data with classification data by: extracting a data signature from the received test data; comparing the extracted data signature to classification data stored in the classification database, wherein the classification data comprises a plurality of data signatures and test results corresponding thereto; and determining a test result based on said comparing.

The processor may be configured to update the classification data stored in the classification database with the test data, the data signature, or both and the corresponding test result received from the computing device associated with the clinician if the test data, the data signature, or both are not previously stored as classification data in the classification database.

The processor may be configured to transmit, via the communication module, results data indicative of the test result received from the computing device associated with the clinician to the suitable computing device associated with the test location.

The one or more predetermined conditions for the processor transmitting the test data, or data associated therewith, to the computing device associated with at least one predetermined clinician is one or both of where the step of processing the received test data with classification data does not result in the determination of a test result, and for testing of accuracy of the processing step.

The processor may be configured to receive, via the communication module, patient data associated with the person associated with the test data, wherein the processor is configured to store the patient data in a suitable patient database storing patient data and transmit the patient data with the test data, or data associated therewith, to the computing device associated with the clinician.

It will be understood that the processor described herein may be one or more server/s which facilitates automated or automatic determination of test results as well as automatic improving of the system by receiving test results and updating the database with input from remote clinicians.

The classification database may comprise classification data comprises data signatures, and corresponding test results; and wherein system comprises the patient database storing patient data associated with people associated the biological sampled being tested, wherein at least some of the patient data is stored for a shorter period of time than the classification data.

The test data may be one or more of an image of a suitable test graph/s generated by the medical test equipment and displayed by a suitable display device associated with the medical test equipment, the suitable test graph/s generated by the medical test equipment, and numerical data associated with the test graph/s generated by the medical test equipment.

The system may comprise or may be interfaced with a suitable data capturing device located at the test location, wherein the suitable data capturing device is configured to capture an image of the suitable of graph/s displayed by the display devices associated with the medical test equipment by way of a suitable test data capturing device provided adjacent the medical test equipment, and/or wherein the suitable data capture device is configured to be interfaced with the medical test equipment so that the suitable test data capturing device is in data communication with the medical test equipment to acquire the suitable test graph/s generated by the medical test equipment and/or the numerical data associated with the test graph/s generated by the medical test equipment.

The processor may be configured to receive the test data from the suitable data capturing device interfaced with the medical test equipment.

It will be appreciated that where appropriate the processor is configured to perform the method steps as described herein.

The PCR test equipment may form part of the system in some example embodiments.

According to another aspect of the invention, there is provided a system for providing test results associated with biological samples tested at a testing location, wherein the system comprises: a classification database storing classification data; a suitable communication module; and a processor arrangement coupled to the classification database and the communication module, wherein the processor is configured to: receive test data acquired from medical test equipment located at a test location, wherein the test data is associated with a test conducted on a biological test sample from a person by the medical test equipment; process the received test data with a classifier trained with, or configured to use, the classification data stored in a classification database to determine a corresponding test result in an automated fashion

, wherein the test result is provided with a performance measurement associated with the determination; and transmit, via the communication module, results data indicative of the corresponding test result to a suitable computing device associated with the test location; wherein if the performance measurement associated with the classification is below a predetermined threshold, the processor is further configured to: transmit the test data, or data associated therewith, to a computing device associated with a clinician capable of interpreting the test data via the communication module; receive a test result corresponding to the transmitted test data, or data associated therewith, from the computing device associated with the clinician via the communication module; and update the classification database with the test data, or data associated therewith, and the corresponding test result received from the computing device associated with the clinician; and wherein if the performance measurement associated with the classification is above the predetermined threshold, the processor is configured to: randomly select and transmit the test data, or data associated therewith, to a computing device associated with a clinician capable of interpreting the test data; receive a test result corresponding to the transmitted test data, or data associated therewith, from the computing device associated with the clinician; and if necessary, update the classification database with the test data, or data associated therewith, and the corresponding test result received from the computing device associated with the clinician.

According to another aspect of the invention, there is provided a method of providing a diagnosis at a point of care (POC) location, wherein the method comprises: receiving test data acquired from at least one suitable medical test equipment located at the POC location, wherein the test data is associated with a test conducted on a test sample from a patient by the at least one medical test equipment in real-time or near real-time; processing the received test data outside of the medical test equipment to determine a diagnosis; and transmitting diagnosis data indicative of the determined diagnosis to a suitable computing device located at the POC location.

According to another aspect of the invention, there is provided a system for providing a diagnosis at a point of care (POC) location, wherein the system comprises: a database storing data; a suitable communication module; and a processor arrangement coupled to the database and the communication module, wherein the processor is configured to: receive test data acquired from at least one suitable medical test equipment located at the POC location, wherein the test data is associated with a test conducted on a test sample from a patient by the at least one medical test equipment; process the received test data outside of the medical test equipment to determine a diagnosis; and transmit, via the communication module, diagnosis data indicative of the determined diagnosis to a suitable computing device located at the POC location.

According to another aspect of the invention there is provided a method of providing test results associated with a biological sample being tested at a testing location, wherein the method comprises: receiving, by a processor at a classification location, test data acquired from medical test equipment located at a test location, wherein the test data is associated with a test conducted on a biological test sample from a person by the medical test equipment, and wherein the classification location is a cloud based location separate from the test location; processing the received test data with a classifier trained with, or configured to use, classification data stored in a classification database to determine a corresponding test result in an automated fashion, wherein the test result is provided with a performance measurement associated with the determination; and transmitting results data indicative of the corresponding test result to a suitable computing device associated with the test location; wherein if the performance measurement associated with the classification is below a predetermined threshold, the method comprises: transmitting the test data, or data associated therewith, to a computing device associated with a clinician capable of interpreting the test data; receiving a test result corresponding to the transmitted test data, or data associated therewith, from the computing device associated with the clinician; and updating the classification database with the test data, or data associated therewith, and the corresponding test result received from the computing device associated with the clinician; and wherein if the performance measurement associated with the classification is above the predetermined threshold, the method comprises: randomly selecting and transmitting the test data, or data associated therewith, to a computing device associated with a clinician capable of interpreting the test data; receiving a test result corresponding to the transmitted test data, or data associated therewith, from the computing device associated with the clinician; and if necessary, updating the classification database with the test data, or data associated therewith, and the corresponding test result received from the computing device associated with the clinician.

According to another aspect of the invention, there is provided a non- transitory computer readable storage medium storing a set of non-transitory computer executable instructions which when executed by a suitable processor, causes the processor to perform one or more of the method steps as contemplated herein.

According to another aspect of the invention, there is provided a positioning device for positioning a data capturing device relative to a display screen associated with medical test equipment, the device comprising: a cradle attachable to a data capturing device for locating the same at a plane substantially parallel to and spaced from the display screen of the medical test equipment; a plurality of legs operatively attached to the cradle, wherein each of the legs are height adjustable to space the cradle from the aforementioned display screen.

According to yet another aspect of the invention, there is provided a system which is configured to:

- collect amplification curve data produced by any real-time PCR device, which may, but does not need to include a physical connection to the PCR device;

- apply a computing algorithm that performs process diagnostics using kurtosis, and the position of the peak of the of the generated data in time, to determine the threshold line and cycle quantification value of the data to immediately display a preliminary binary positive or negative value at the point of care;

- receive additional patient metadata from an on-site healthcare worker electronically;

-store the data will be locally and transmitting the data, along with relevant patient clinical information, via a communication link to a cloud-based server and displayed as a web-based dashboard;

- verify the result with a tele-clinician making informed clinical recommendations based on the real-time PCR process data in combination with the patient metadata in addition to their expert knowledge of the treatment of specific conditions;

- provide a management view of this data to government to have realtime location-based testing information.

It will be understood that descriptions directed to one aspect of the invention described herein may be applicable mutatis mutandis to other aspects of the invention. Moreover, the numbering of the various aspects of the invention do not in any way constitute a ranking of said aspects of the invention. BRIEF DESCRIPTION OF DRAWINGS

The objects of this invention and the manner of obtaining them, will become more apparent, and the invention itself will be better understood, by reference to the following description of embodiments of the invention taken in conjunction with the accompanying diagrammatic drawings, wherein:

Figure 1 shows a network showing an example embodiment of a system for providing a test result in accordance with an example embodiment of the invention;

Figure 2 shows a conceptual schematic diagram of a data capturing device in accordance with an example embodiment of the invention interfaced with the PCR equipment via a mechanical positioning device in accordance with an example embodiment of the invention;

Figure 3 shows a perspective view of a positioning device for the data capturing device in accordance with an example embodiment of the invention forming part of the system in accordance with an example embodiment of the invention;

Figure 4 shows a perspective view of the positioning device of Figure 3 with a data capturing device of Figure 2 operatively located in a cradle defined thereby;

Figure 5 shows a perspective view of a positioning device of Figure 4 with the data capturing device operatively attached thereto in use, located relative to a display screen associated with medical test equipment in accordance with an example embodiment of the invention;

Figure 6 shows another perspective view of the positioning device of Figure 4 with the data capturing device operatively attached thereto in use, located relative to a display screen associated with medical test equipment in accordance with an example embodiment of the invention;

Figure 7 shows a high-level flow diagram of a method in accordance with an example embodiment of the invention for providing a test result at a test location in accordance with an example embodiment of the invention;

Figure 8 shows a high-level flow diagram of a method in accordance with an example embodiment of the invention for acquiring test data in accordance with an example embodiment of the invention;

Figure 9 shows another high-level flow diagram of a method in accordance with an example embodiment of the invention for acquiring test data in accordance with an example embodiment of the invention;

Figure 10 shows another high-level flow diagram of a method in accordance with an example embodiment of the invention for transmitting test data in accordance with an example embodiment of the invention;

Figure 11 shows another high-level flow diagram of a method in accordance with an example embodiment of the invention for processing the received test data in accordance with an example embodiment of the invention;

Figure 12 shows an example representation of a typical PCR, particularly qPCR, curve(s) in accordance with an example embodiment of the invention;

Figure 13 shows a lower level flow diagram of a method in accordance with an example embodiment of the invention for processing the received test data in accordance with an example embodiment of the invention; Figure 14 shows flow diagram of a method in accordance with an example embodiment of the invention for scaling the received test data in accordance with an example embodiment of the invention;

Figure 15 shows flow diagram of a method in accordance with an example embodiment of the invention for processing the received test to determine the validity of the received test data in accordance with an example embodiment of the invention;

Figure 16 shows flow diagram of a method in accordance with an example embodiment of the invention for processing the received test to extract a data signature or data key points in accordance with an example embodiment of the invention; and

Figure 17 shows a diagrammatic representation of a machine in the example form of a computer system in which a set of instructions for causing the machine to perform any one or more of the methodologies discussed herein, may be executed.

DETAILED DESCRIPTION OF AN EXAMPLE EMBODIMENT

The following description of the invention is provided as an enabling teaching of the invention. Those skilled in the relevant art will recognise that many changes can be made to the embodiment described, while still attaining the beneficial results of the present invention. It will also be apparent that some of the desired benefits of the present invention can be attained by selecting some of the features of the present invention without utilising other features. Accordingly, those skilled in the art will recognise that modifications and adaptations to the present invention are possible and can even be desirable in certain circumstances and are a part of the present invention. Thus, the following description is provided as illustrative of the principles of the present invention and not a limitation thereof.

It will be appreciated that the phrase “for example,” “such as”, and variants thereof describe non-limiting embodiments of the presently disclosed subject matter. Reference in the specification to “one example embodiment”, “another example embodiment”, “some example embodiment”, or variants thereof means that a particular feature, structure or characteristic described in connection with the embodiment(s) is included in at least one embodiment of the presently disclosed subject matter. Thus, the use of the phrase “one example embodiment”, “another example embodiment”, “some example embodiment”, or variants thereof does not necessarily refer to the same embodiment(s).

Unless otherwise stated, some features of the subject matter described herein, which are, described in the context of separate embodiments for purposes of clarity, may also be provided in combination in a single embodiment. Similarly, various features of the subject matter disclosed herein which are described in the context of a single embodiment may also be provided separately or in any suitable sub-combination.

Referring to Figure 1 of the drawings, there is provided a network N incorporating a system 10 for providing a test result associated with a medical test performed on a biological sample from a patient P by medical test equipment 12 (F/U 2.0) located at a test location L1 to a suitable computing device 14 (F/U 3.0) associated with the test location L1 in an automated fashion.

The test location L1 is typically a point of care (POC) location, for example, a hospital, clinic, medical testing facility, or the like where under certain conditions, for example, during times of pandemic, there is a shortage of suitably trained or skilled clinicians in the form of doctors, pathologists, nurses, or the like trained to interpret test results from medical test equipment 12 in order to diagnose a disease. This problem may result in shortage of beds at hospitals as people wait for test results, erroneous test results and incomplete data pertaining to infection rates, etc. which may result in incorrect or ineffective corrective actions and interventions being taken, etc.

Reference will be made to the COVID-19 pandemic where medical testing equipment in the form of Polymerase chain reaction (PCR) test equipment, typically real-time PCR (qPCR), are is used to process samples of biological material from patients P so as to facilitate test results for or diagnosis of COVID-19 being determined to be positive, negative, or, in some instances, inconclusive. However, nothing precludes the invention disclosed herein being used for other medical testing equipment not described herein. Notwithstanding, in the present disclosure, the system 10 has been specifically designed to cater for PCR testing equipment, particularly insofar as COVID-19 testing is concerned and, in an environment, where there is a shortage of skilled clinicians to be able to interpret PCR curves.

In this regard, the system 10 as described herein provides a means by which the processing of PCR test results can be expedited via a distributed cloud-based computing system 10 which is not necessarily provided at the POC location L1 but which processes test data acquired from the PCR equipment 12 in a remote automated cloud-based fashion to automatically provide a test result or diagnosis to the computing device 14 associated with a POC clinician located at the POC location L1 , and wherein where a diagnosis cannot be made in an automated fashion as will be described below, a remote clinician RC is called upon automatically via their associated computing device 17 (F/U 6.0) to provide a test result or diagnosis based on test data acquired from the PCR test equipment 12.

Though only one of each is illustrated, it will be noted that the system 10 as described herein may be used to receive and process test results from a plurality of test equipment 12 distributed throughout the network N. In addition, the system 10 may be used to provide test results or diagnoses in an automated remote fashion for multiple POC locations L1 and may engage with a plurality of POC and clinicians LC, RC as will be understood by those skilled in the field of invention but for ease of illustration only one of each aspect of the invention disclosed herein is illustrated.

The system 10 comprises a processor 16 (F/U4.0), a classification database 18 (F/U 5.0), and a suitable communication module (provided in the processor 16 in the present illustration as will be described below) to facilitate communication of the processor 16 over a conventional communication network 20. The network 20 may comprise one or more different types of communication networks. In this regard, the communication networks may be one or more of the Internet, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), various types of telephone networks (e.g., Public Switch Telephone Networks (PSTN) with Digital Subscriber Line (DSL) technology) or mobile networks (e.g., Global System Mobile (GSM) communication, General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), and other suitable mobile telecommunication network technologies), or any combination thereof. It will be noted that communication within the network may achieved via suitable wireless or hard-wired communication technologies and/or standards (e.g., wireless fidelity (Wi-Fi®), 4G, long-term evolution (LTE ^TM ), WiMAX, 5G, and the like). In some example embodiments, the system 10 may be coupled to other elements of the communications network 20 via dedicated communication channels, for example, secure communication networks in the form of encrypted communication lines (e.g. SSL (Secure Socket Layer) encryption).

The processor 16 (F/U4.0) may be one or more processors in the form of programmable processors executing one or more computer programs to perform actions by operating on input test data and generating output result data indicative of a test result. The processor 16, as well as any computing device referred to herein, may be any kind of electronic device with data processing capabilities including, by way of non-limiting example, a general processor, a graphics processing unit (GPU), a digital signal processor (DSP), a microcontroller, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or any other electronic computing device comprising one or more processors of any kind, or any combination thereof. For brevity, steps described as being performed by the system 10 may be steps which are effectively performed by the processor 16 and vice versa unless otherwise indicated.

The system 10 may comprise a suitable memory device (not shown) in the form of a computer-readable medium including system memory and including random access memory (RAM) devices, cache memories, non- volatile or back-up memories such as programmable or flash memories, readonly memories (ROM), etc. In addition, the memory device may be considered to include memory storage physically located elsewhere in the system 10, e.g. any cache memory in the processor 16 as well as any storage capacity used as a virtual memory, e.g., as stored on a mass storage device.

Though not illustrated, it will be appreciated that the system 10 may comprise one or more user input devices (e.g., a keyboard, a mouse, imaging device, scanner, microphone) and one or more output devices (e.g., a Liquid Crystal Display (LCD) panel, a sound playback device (speaker), switches, valves, etc.).

It will be appreciated that the computer programs executable by the processor 16 may be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. The computer program may, but need not, correspond to a file in a file system. The program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a mark-up language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code). The computer program can be deployed to be executed by one processor 16 or by multiple processors, even those distributed across multiple locations, for example, in different servers and interconnected by the communication network 14.

The computer programs stored in the memory device typically contains instructions which are arranged to cause the processor 16 to perform the methods described below with reference to Figures 7 to 16.

The system 10 may include one or more of a back-end (e.g., a data server), a middleware (e.g., an application server), and a front-end (e.g., a client computing device having a graphical user interface (GUI) or a Web browser through which a user can interact with example implementations of the subject matter described herein). In particular, for ease of illustration and explanation, it will be understood that the processor 16 for the purpose of the present disclosure may be in the form of or embodied in a backend server 16 configured to process test data in a manner described herein. It follows that the processor 16 and the server 16 as described herein and as illustrated in Figure 1 may be referred to interchangeably.

The classification database 18 may be similar to the memory device described herein but stores a plurality of data signatures associated with test data and associated test results corresponding to the data signatures as described herein.

In particular, the processor 16 is configured to receive test data acquired by a suitable data capturing device 22 (F/U 1 .0) in a wireless fashion over the communication network 20.

Turning now to Figure 2 where a high-level block diagram illustration of the data capturing device 22 interfaced with the PCR equipment 12 is provided. The device 22 may be a custom-built device having a suitable HMI (Human Machine Interface), power source, GPS (Global Positioning System) module), image capturing device in the form of camera, a memory device, a processor (similar to the processor described above although not in the form of a server as will be appreciated by those skilled in the art, etc.), wireless communication module, and a serial communication interface provided in a suitable housing. The device 22 may be a re-purposed computing device such as a smartphone, tablet computer, or the like having the aforementioned features. In one example embodiment, the device 22 may comprise a suitable POC software module configured to acquire data from the PCR equipment 12 and transmit the same to the server 16. The software module may be a suitable software application downloadable by the device 22.

The software module may be configured to prompt the POC clinician LC for patient data (gender, age, locale, and any other relevant symptoms or comorbidities (in the case of COVID-19)).

As alluded to above, the POC location L1 may comprise a plurality of devices 22 which are usually linked to the number of PCR test equipment provided at the POC location L1. Moreover, it will be noted that in some example embodiments, the device 14 and the device 22 are the same device which may comprise the software module or application (or “app” as it is colloquially referred to) as contemplated herein.

Notwithstanding, in many example embodiments, the devices 14 and 17 being in the form of conventional mobile computing devices such as smartphones able to communicate wirelessly with the server 16 over the network 20 to receive and transmit data. The devices 14 and 17 may have suitable apps downloaded thereon to facilitate the communication with the server 16 contemplated herein.

In the case where the device 22 is a bespoke device or even a conventional device, for example, re-purposed by way of the suitable software application, the device 22 is required to be interfaced with the PCR equipment 12. In this way, the system 10 is invariant to specific types or brands of PCR equipment .

In some example embodiments, the device 22 is interfaced with the PCR equipment 12 in a hard wired or wireless fashion to be able to acquire test data in the form of numerical data associated with suitable PCR curves or graphs generated by the PCR equipment, or the actual PCR curves or graphs. In one example, embodiment, the device 22 is interfaced with the PCR equipment 12 in a hardwired fashion via a Universal Serial Bus (USB) to facilitate serial communication with the PCR equipment 12 thereby to acquire numerical data associated with the PCR curves or graphs generated by the PCR equipment 12, or the actual PCR graphs, in a conventional fashion.

Turing to Figures 3 to 6 of the drawings, it will be noted that in some example embodiments, where an interface to acquire the test data from the PCR equipment 12 in a manner contemplated above is not possible, the capturing device 22 is interfaced with a suitable display screen D of PCR equipment 12 so as to be able to capture an image of the conventional PCR curves and/or graphs generated and displayed by the display D associated with the PCR equipment 12. To this end, the system 10 may comprise a positioning device 24 as illustrated more clearly in Figures 3 to 6 which may be used to position the device 22 relative to the display D of the PCR equipment so that the camera of the device 22 is able to capture an image of the display D, particularly of the display D displaying the PCR curve or graph as illustrated in Figure 12.

The device 24 comprises a suitable cradle 26 attachable to the device 22 without obscuring the camera associated therewith. The device 24 further comprise a plurality of height adjustable legs 28 to adjust the height of the cradle 26, and thus the capturing device 22 from the display D in order to capture an image of the display screen D, for example, in a predetermined manner. For example, for a PCR equipment of type X, the height of the cradle and device 22 from the display D must be set at a particular height H (Figure 6). To this end, the legs 28 may be telescopically extendable to vary the height of the cradle 26 and thus the device 22 operatively attached thereto.

In one example embodiment, the cradle comprises a square frame having an internal void. The telescopically extendable legs 28 may be operated by way of suitable screws, etc.

The device 24 maintains device stability during the image capturing process, assists in positioning the capturing device 22 at a suitable distance from the PCR equipment 12, and provides repeatable alignment with the output display D of the PCR equipment 12.

It will be noted that though the PCR equipment 12 itself is excluded from the scope of the present disclose solution, the PCR curves/graphs and/or its numerical equivalent generated by the PCR equipment in a conventional fashion plays a central role in the solution described herein.

The device 22, and the software modules operating on the devices 14 and 17 may, for the purposes of this disclosure, be considered part of the system 10.

In any event, turning back to Figure 1 , it will be noted that a medical sample is typically obtained from a patient P and subjected to analysis by means of the PCR equipment 12 (F/U 2.0) in a conventional fashion. By means of the data capturing device 22 (F/U 1.0), test data generated by the PCR equipment 12 and associated with the sample, is acquired and transmitted to the processor 16 in the form of the centralised server (F/U 4.0). The processor 16 receives the test data over the network 20.

Simultaneously to the data transmission from the device 22 (F/U 1 .0) the POC clinician LC records the patient data (gender, age, locale, and any other relevant symptoms or comorbidities (in the case of COVID-19) via their device 14 (F/U 3.0). The patient data is also transmitted to the processor 16 but may be temporarily stored in a suitable patient database (not shown) and/or locally.

The processor 16 (F/U 4.0) is programmed and/or configured to determine or extract a data signature from the test data received from the device 22.

In one example embodiment, the processor 16 conveniently implements or provides a suitable classifier which configured to compare the extracted data signature to other signatures of the same types stored in the classification database 18 of known data signatures.

In another example embodiment, the processor 16 conveniently implements or provides a suitable classifier in the form of a machine-based learning (ML) classifier trained with data stored in the classification database 18. In this regard, the ML classifier may be configured to use the extracted data signature as an input in order to determine the test result.

It will be noted that the ML classifier is trained with the classification data in the classification database but in doing so, feature extraction is performed using known characteristics of a PCR curve to perform clustering. Input from a clinician is used to create the labels for the clusters - therefore supervised learning.

Initially all test data is routed to the clinician for labeling to create a classification database which serves as a training/learning database. The random selection of the test data for transmission to the clinician even beyond the performance measure, or in other words even after a confidence threshold for the ML classifier is reached, allows for the ML classifier trained by way of supervised learning to adapt to changes in observation over time.

In other words the novel aspect is t the architecture change in the classification process over time using human expertise to track movement in the input population clusters. In other words, if the signature of the virus changes over time, we will be able to keep track of it and adapt with it.

From the foregoing, those skilled in the art will recognise that the classifier may be implemented as a classical statistical classifier, machine-learning based classifier, or a combination of several algorithms of the preceding types depending on the nature of the input data, either graphs or numerical representation of test results.

If a successful classification could be made, result data indicative of the test result corresponding to a matching data signature in the database 18 is transmitted back to the POC clinician LC and displayed via the devices 14(F/U 3.0) and/or 22 (F/U 1 .0). In this regard, it will be appreciated that a successful classification occurs when the classifier determines the test result with a performance measurement within a particular performance threshold, for example, between 95% and 99% performance threshold, particularly a 95% performance threshold. The performance measurement may be understood by those skilled in the art as a measure of how closely the extracted data signature matches the data signatures of the same type stored in the database 18 and/or the confidence/performance of the machine-learning based classifier.

In the event that a successful classification is made, the processor 16 is configured to randomly select test data which, together with patient data, is transmitted over a communications network (not shown but it may be similar to the network 20) to the clinician RC via the device 17. The random selection may be based on a statistically random selection, for example, based on the number of test results processed, etc. In the event that a classification cannot be made, or in other words, the classifier determines the test result with a performance measurement below the predetermined threshold, i.e., below 95%, the test data, together with patient data is transmitted over a communications network (not shown but it may be the same as the network 20) to the clinician RC via the device 17.

The clinician RC is suitably trained to perform test classification and to provide test results based on the received test data. It will be noted that in the case of the test data being an image, the processor 16 may be configured to transmit the image to the clinician RC. However, in the case of the test data being in the form of numerical test data, the processor 16 may be configured to generate suitable PCR curves/graphs based on the numerical test data and send the same to the clinician as they are usually trained to analyse the PCR curves and graphs and not necessarily raw numerical data.

In one example, embodiment, the clinician RC may be authorised to receive test data for validation from the processor 16. In this respect, the authorisation may be a pre-authorisation so that only so-called trusted clinicians RC ay be permitted to classify test data associated with data signatures which the system 10 does not have stored in the database 18.

In any event, the test result which comprises a suitable classification of the test data by the clinician RC is transmitted back to the POC clinician via the device 14 (F/U 3.0) and/or 22 (F/U 1.0). Additionally, the classification database 18 is updated with the data signature of the classification by the clinician RC for use in future classifications. In the example embodiment wherein the classifier is a machine-based learning classifier, the updated classification database 18 is used to train the classifier. The training of the classifier may be periodic or ad hoc based on the number/amount of updates to the classification database 18.

In updating the classification database the RC may update the database directly or the update of the database may occur based on certain extracted features of the sample subject to validation based on the requirements of the classifier. As previously mentioned, automatically classified samples which have a classification with a performance measurement above the predetermined threshold are subjected to validation by a validating clinician RC based on a statistically significant random selection.

Reference will now be made to Figures 7 to 16 of the drawings where various process flow diagrams of methods and/or processes in accordance with example embodiments of the invention are illustrated. Though nothing precludes the methods and/or processes described below from being carried out by systems not described herein, the methods and/or processes described below will be explained further with reference to the system 10, and particularly the processor 16, as described herein carrying out all or the majority of the steps described herein. In this regard, the operation of the system 10 and the processor 16 will be further described and/or will be apparent to those skilled in the field of invention based on the description which follows below. Moreover, it will be understood that some of the methodologies outlined below may be well understood by those skilled in the art, for example, with reference the aforementioned disclosures relating to the extraction of the data signatures and processing of the same to automatically classify test data and provide test results. Notwithstanding, the explanation which follows regarding automatic processing of PCR data may be viewed in light of the disclosures hereinbefore mentioned which provide more detailed explanations of the techniques contemplated herein and which may be used by the system described herein to classify test data.

In Figure 2, a high-level method in accordance with an example embodiment of the invention is generally indicated by reference numeral 30.

Once the PCR equipment 12 has processed a biological sample from a patient P, at block 32, the method 30 comprises acquiring the test data from the PCR equipment 12, at blocks 34 (F 2.0), 36 (F3.0) by way of the device 22.

It should be noted that F 2.0 and F 3.0, in essence, could refer to the same test data, although, in practice, PCR equipment 12 only provides either of the output mechanisms. In particular, it will be noted that the PCR equipment 12 will provide the analysis result in either a graphical format (printed, on-device graphical display, attached PC display), block 34, or via a data connection to connected equipment (typically in some interchangeable format such as CSV), block 36. Block 34 (F 2.0) therefore makes provision for graphical data while block 36 (F 3.0) handles the case of numerical data.

Turning to Figures 8 and 9 of the drawings where the method steps 34 and 36 are expanded upon. In Figure 8, in obtaining the test data in the form of an image of the PCR curve/graph, the capturing device 22 is positioned, at block 40, relative to the display screen D of the PCR equipment 12 to capture images of the generated PCR curves/graph/s.

The area and axis limits of the PCR curve/graph may be defined, at blocks 42, 44, and the image/s are captured at block 46 using the camera of the device 22 in a conventional fashion.

In the case where the device 22 is interfaced in a serial fashion to obtain test data in the form of numerical data/graph/s from the PCR equipment 12, the methods 36 comprises connecting, at block 48, the capturing device 22 to the PCR equipment, for example, via a USB connection.

The method 36 then comprises downloading, for example, in a serial fashion, the numerical data corresponding to the PCR curves/graphs generated by the PCR equipment and/or the actual PCR curves/graphs to the capturing device 22.

The method 36 then comprises defining axis limits at block 52.

Turning back to Figure 7, the method 30 comprises, capturing, at block 54, patient data associated with the patient P associated with the test sample being tested by the PCR equipment. The capturing of patient data at block 54 (F 4.0 in Figure 7) is dependent on the exact condition and is not explored in detail herein. It is expected that all data that may pertain to the generation of a clinical test result would be captured. The patient data may be received and stored locally, for example, by the device 22.

The method 30 then comprises transmitting, at block 56, the test data acquired by the device 22 to the processor 16 embodied in the remote central server 16. The test data is received by the processor 16 from the device 22 over the network 20.

Figure 10 shows the transmitting step contained in block 56 of Figure 7 in more detail. In particular the test data and patient data acquired are stored locally at blocks 58, 60 , wherein the test data and patient data are combined and encrypted at blocks 62 and 64 respectively to generate an encrypted data payload.

The method 56 then comprises, developing, at block 65, a signature hash of the encrypted data payload before connection with the remote server 16 is established at block 66.

The method 56 comprises authenticating the PCR test equipment 12 to the processor 16. It follows that the processor 16 may be configured only to process test data associated with authorised and/or authenticated test equipment 12, at block 66.1 .

The method 56 may comprise encrypting the uploaded data at block 67 and uploading the test data to the server 16, at block 68.

The method 56 further comprises performing an upload validation at block 69 to determine that the test data uploaded has been done so successfully or unsuccessfully.

Once the test data is successfully uploaded to the server 16, the method 56 comprises disconnecting from the server 16 at block 70. It will be noted that some of these steps may be achieved with the suitable software application operating on the capturing device 22.

Turning back to Figure 7, once the test data is received by the processor 16 at the cloud-based remote location separate from the POC location L1 , the method 30 comprises processing the test data to determine a test result in an automated fashion at block 72.

Figure 11 shows the method step contained in block 72 of Figure 7 in more detail. In particular, the method 72 comprises deconstructing, at blocks 73, 74, the data payload received by the processor 16 to provide PCR test data and patient data in a known format (F 6.1 and F 6.2). At block 75 (F 6.3) a numerical representation of the test data is obtained. In this regard, turning to Figure 13 of the drawings, the method step contained in block 75 of Figure 11 is shown in more detail.

Reference is also made to Figure 12 where an example qPCR curve is depicted, the curve (more specifically a set of curves) is comprised of the positive control curve (which demonstrates that a known control compound has reacted as expected) a negative control curve (opposite of positive control curve) and the result curve.

In any event, the method 75 comprises determining, at block 76, if the graphical test data is present in the test data extracted from the encrypted data payload.

The method 75 comprises, detecting a positive control curve at block 77, detecting a negative control curve at block 78, and detecting a test result curve at block 79.

The method 75 then comprises scaling the curve to axis limits, at block 80. It should be noted that image processing techniques (primarily morphological operations and affine transforms) will be used for the detection of lines in the image. The PCR curves are typically sigmoidal in shape and can thus be discerned from (possible) background grid lines or other image information. The positive control curve is also non-linear but exhibits a compound growth curve and, again is discernible from possible background artifacts in the image. The negative control curve is near the baseline (zero value on the vertical axis) but is not completely linear, a curve fitting between the start and end points of the candidate control curve would facilitate discernment from possible background information.

Given that the image is scale agnostic at this point the scale data is used to transform the fitted curves to those based on a known scale. Once the requisite scaling of the curves has been completed it is a simple task to extract scaled numerical data from the image.

It will be appreciated that the amplification cure may be evaluated to determine validity of the sample using the control curves. If the control curves do not exhibit the expected amplification characteristics, the sample is rejected (labelled as invalid), if not - the complete analysis and classification described herein is followed.

In the case that the data present is already in numerical format, the method proceeds to determining the validity of the test results in block 95 of Figure 11 .

In any event, Reference is made also now to Figure 14 where the method step 80 for scaling the PCR curve is expanded on. It will be noted that this is typically in the case where the test data is in the form of an image captured by the device 22.

Essentially, the area that is defined by the user in steps 42 and 44 of Figure 8 is used as an approximate enclosing area of the test data pertaining to the PCR curve/graph.

There will be some "whitespace" that surrounds the plot axis, and this surrounding whitespace is not equally distributed. The results in a perspective error commonly referred to as the keystone distortion of the image.

In short, the general image scaling step 80 transforms the image data from the test data from a pixel grid to a new domain that (may have) differing scales / units on the vertical / horizontal axis. Primarily this is done by performing curve fitting on the pixel data and then substituting the (x,y) pixel coordinates in the fitted curve equation with the pixel/unit information. The net effect of this is that the curve has been transformed in a manner that would be consistent with a human process of interpreting a graph.

However, in particular, the method 80 comprises determining at block 81 a keystone error in the image at block 81 .

The method 80 comprises performing, at block 82, an affine transform to correct the keystone error.

The method 80 comprises locating the origin of the plot axis (pixel X, Y) at block 83, locating the vertical axis limit (pixel X, Y) at block 84, and locating the horizontal axis limit (pixel X, Y) at block 85.

The method 80 comprises determining the vertical scale (unit/pixel) at block 86 and the horizontal scale (unit/pixel) at block 87. The pixel data of the positive control curve to axis units is mapped at block 88. Similarly, the pixel data of the test curve to axis units is mapped at block 89 and pixel data of the negative control curve to axis units is mapped at block 90.

The method 80 comprises performing curve fitting at block 91 to positive control curve, performing curve fitting at block 92 to the test or result curve, and performing curve fitting at block 93 to the negative control curve.

Turning back to Figure 13, the method 75 comprises the step of extracting the numerical representation of the PCR curve/graph at block 94.

Turning back to Figure 11 , the method comprises determining, at block 95, the validity of the test, wherein the test data is only processed further if the test data is valid. Reference is made also now to Figure 15 where the method step 95 for determining the validity of the test data is expanded on with reference as well to Figure 12.

Typically, the threshold value and result curve intersection point in the PCR curve is used to indicate the start of Phase 2 of the test executed by the PCR test equipment 12.

In reference to the Phases mentioned herein, it will be noted by those skilled in the art that in conducting tests using a PCR process such as that undertaken by the PCR test equipment mentioned herein, there are three phases of PCR amplification: exponential, linear, and plateau. The exponential phase is the first phase of PCR amplification, or Phase 1. Here, reaction components are in excess, there is an exact doubling of product each cycle, and the reaction is specific and precise. Real-Time PCR measures the Cq value at this phase of PCR.

The linear phase is the second phase of PCR amplification, or Phase 2. Here, the reaction components are being consumed, amplification slows, and the reactions become highly variable.

The final phase of PCR amplification is the plateau phase, or Phase 3. In this phase, the reaction is complete and no more products are being generated. Traditional PCR takes its measurements during this phase of PCR. In any event, prior to this point Phase 1 is active. Phase 2 continues until the inflection point is reached, at which point Phase 3 commences.

In this regard, the method 95 comprises determining the validity of the test data by determining, at block 96 and 97, whether both positive and negative control curves are present in the test data.

The method 95 comprises determining whether or not the result curve is bounded by the positive and negative control curves in block 98.

The method 95 then comprises determining whether or not the growth coefficient of the result curve in Phase 1 is typically a doubling in value per cycle (typically a value of 2 is ideal although >= 1 .8 is acceptable).

If the steps 96 to 99 are in the affirmative, the method 95 classifies the test data as valid at block 100. If any of the steps 96 to 99 is in the negative, then the test data is considered invalid, at block 102.

Turning back to Figure 11 , if the test data is valid, the method 72 comprises extracting key points from the test data, at block 103, in other words, extracting the data signature from the test data. Reference is now made to Figure 16 where the method step 103 of Figure 11 is expanded on in more detail.

The method 103 comprises extracting the data signature by extracting and/or determining the start and end points of Phase 2 of the PCR curve at blocks 104, 105.

The method 103 then comprises determining the gradient of the result curve in Phase 2 at block 106. The key points of the start and end of Phase 2 of the results curve and the gradient of the results curve of the PCR curve extracted and/or determined in the method step 103 may form the data signature as contemplated herein.

Turning back to Figure 11 , wherein the method 72 comprises comparing the extracted and/or determined data signature in step 103 to the plurality of data signatures stored in the classification database 18 at block 107. Though not expressly mentioned in Figure 11 , in the case of the classifier being in the form of a machine-based learning (ML) classifier, the method comprises using the extracted and/or determined data signature in step 103 as an input to the ML classifier trained with the plurality of data signatures stored in the classification database 18 at block 107.

In response to determining a match and/or a determination by the classifier with a performance measurement/measure/value which is above the threshold, a corresponding test result to the matched data signature is obtained or determined, for example, from the classification database and the classification result is generated at block 108. This may be in the case of COVID-19 testing a positive or a negative COVID-19 test result.

Similarly, the ML classifier is configured to determine a test result based on the extracted and/or determined data signature as will be understood by those skilled in the art.

It will be noted that if comparison contemplated in step 107 does not find a suitable match, in other words if the performance measure is below the predetermined threshold, meaning that there is no substantially similar signature stored in the classification database 18 and/or the ML classifier determines the test result with a performance measure below the threshold, the method 72 comprises transmitting the test data to the remote clinician RC, particularly their computing device 17. For example, this may be via the software app described earlier downloaded on the mobile computing device of the clinician RC, whom may be an authorised clinician for the purposes of this disclosure. The same may be done where extraction in the step 103 could not be performed.

The method 72 ay comprise transmitting the patient data as well to the clinician RC to enable the clinician RC to recommend suitable treatment protocols based on certain physiological parameters associated with the patient P. In this regard, the method 72 comprises, receiving from the clinician, their classification of the associated test data and capturing the same together with defining the key parameters associated with the test data which was classified by the clinician at blocks 110, 112.

The method 72 then comprises calculating the test result parameters and determining a data signature associated with the test data classified by the clinician RC at block 1 14.

The method 72 comprises updating the classification database 18 by storing the determined data signature and associated classification or in other words the test result determined by the clinician in the classification database 18 to be used in future classification and/or training of the ML classifier. The updating of the database 18 may be also with treatment plans associated with the test result and based on the patient data.

As mentioned herein, in the event that a successful classification is made, i.e., the classifier determines a test result with a performance measure above the predetermined threshold, the processor 16 is configured to randomly select test data which, together with patient data, is transmitted over a communications network (not shown but it may be similar to the network 20) to the clinician RC via the device 17. The random selection may be based on a statistically random selection, for example, based on the number of test results processed, etc.

This mechanism allows for the continual improvement and updating of the classification database 18 organically and in a manner, which takes into account feedback from skilled clinicians. The mechanism also provides for the real-time addition of new pathogen signatures to the database 18 and provides a rationale for classification results generated based on a humangenerated pathogen database which has had specialist input.

Turning back to Figure 7 of the drawings, wherein it will be noted that of the processor 16 is able to automatically classify the test data, the method 30 proceeds in real-time and/or substantially real-time in an automated fashion from the time of receipt of the test data and the patient data.

In any event, once the test result has been received, the method 30 comprises transmitting, at block 120, results data comprising the determined test result to the device 22 and/or 14 at the POC location L1. The method 30 may optionally comprise determining and transmitting a treatment programme to the device 22 and/or 14.

In some example embodiments, the method 30 comprises transmitting a script for medication which may be automatically printed at the POC location L1 by a suitable printer communicatively coupled to the device 22 and/or the device 14.

In some example embodiments, the test result may be validated at block 122 by a clinician.

Referring now to Figure 17 of the drawings which shows a diagrammatic representation of a machine in the example of a computer system 200 within which a set of instructions, for causing the machine to perform any one or more of the methodologies discussed herein, may be executed. In other example embodiments, the machine operates as a standalone device or may be connected (e.g., networked) to other machines. In a networked example embodiment, the machine may operate in the capacity of a server or a client machine in server-client network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine may be a personal computer (PC), a tablet PC, a set-top box (STB), a Personal Digital Assistant (PDA), a cellular telephone, a web appliance, a network router, switch or bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine. Further, while only a single machine is illustrated for convenience, the term “machine” shall also be taken to include any collection of machines, including virtual machines, that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein. In any event, the example computer system 200 includes a processor 202 (e.g., a central processing unit (CPU), a graphics processing unit (GPU) or both), a main memory 204 and a static memory 206, which communicate with each other via a bus 208. The computer system 200 may further include a video display unit 210 (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)). The computer system 200 also includes an alphanumeric input device 212 (e.g., a keyboard), a user interface (Ul) navigation device 214 (e.g., a mouse, or touchpad), a disk drive unit 216, a signal generation device 218 (e.g., a speaker) and a network interface device 220.

The disk drive unit 216 includes a non-transitory machine-readable medium 222 storing one or more sets of instructions and data structures (e.g., software 222) embodying or utilized by any one or more of the methodologies or functions described herein. The software 222 may also reside, completely or at least partially, within the main memory 204 and/or within the processor 202 during execution thereof by the computer system 200, the main memory 204 and the processor 202 also constituting machine-readable media. The software 222 may further be transmitted or received over a network 226 via the network interface device 220 utilizing any one of a number of well-known transfer protocols (e.g., HTTP). Although the machine-readable medium 222 is shown in an example embodiment to be a single medium, the term "machine-readable medium" may refer to a single medium or multiple medium (e.g., a centralized or distributed memory store, and/or associated caches and servers) that store the one or more sets of instructions. The term "machine- readable medium" may also be taken to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by the machine and that cause the machine to perform any one or more of the methodologies of the present invention, or that is capable of storing, encoding or carrying data structures utilized by or associated with such a set of instructions. The term "machine-readable medium" may accordingly be taken to include, but not be limited to, solid-state memories, optical and magnetic media, and carrier wave signals.

While the invention has been described in detail with respect to a specific embodiment and/or example thereof, it will be appreciated that those skilled in the art, upon attaining an understanding of the foregoing may readily conceive of alterations to, variations of and equivalents to these embodiments. Accordingly, the scope of the present invention should be assessed as that of the claims and any equivalents thereto. The present invention provides a system which provides a remote interpretation and communication system to, at least partially, overcome or ameliorate the above-mentioned challenges with POC testing with shortage of skilled personnel to assist. It is a further object of the invention to provide clinicians with data on the real-time severity of a specific condition at a specific location as derived from recorded data which can then be analysed over time, which in turn may improve preventative measures within a geographic area where a high prevalence of a specific disease is measured (such as, amongst others, but not limited to, the COVID-19 pandemic).